no code implementations • 31 Oct 2023 • David Marwood, Shumeet Baluja, Yair Alon
Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts.
no code implementations • 4 May 2021 • Shumeet Baluja
We present an automated method to transform an image to a set of binary textures that represent not only the intensities, but also the colors of the original.
no code implementations • 11 Jun 2019 • Michele Covell, David Marwood, Shumeet Baluja, Nick Johnston
We show results that are within 1. 6% of the reported, non-quantized performance on MobileNet using only 40 entries in our table.
no code implementations • 6 Dec 2018 • Shumeet Baluja, Dave Marwood, Nick Johnston, Michele Covell
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints.
no code implementations • 24 Sep 2018 • Shumeet Baluja, David Marwood, Michele Covell, Nick Johnston
For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference.
no code implementations • 7 Sep 2018 • David Marwood, Pascal Massimino, Michele Covell, Shumeet Baluja
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints.
no code implementations • 16 Jan 2018 • Shumeet Baluja
Surprisingly, we find that despite reducing the number of values that can be represented in the output activations from $2^{32}-2^{64}$ to between 64 and 256, there is little to no degradation in network performance across a variety of different settings.
1 code implementation • NeurIPS 2017 • Shumeet Baluja
Steganography is the practice of concealing a secret message within another, ordinary, message.
2 code implementations • 28 Mar 2017 • Shumeet Baluja, Ian Fischer
We efficiently train feed-forward neural networks in a self-supervised manner to generate adversarial examples against a target network or set of networks.
no code implementations • 21 Mar 2017 • Shumeet Baluja
To represent the search space concisely and accurately, the deep networks must encode information about the underlying parameter interactions and their contributions to the quality of the solution.
no code implementations • 3 Feb 2017 • Shumeet Baluja, Michele Covell, Rahul Sukthankar
Real-time optimization of traffic flow addresses important practical problems: reducing a driver's wasted time, improving city-wide efficiency, reducing gas emissions and improving air quality.
1 code implementation • 13 Mar 2016 • Shumeet Baluja
Typography is a ubiquitous art form that affects our understanding, perception, and trust in what we read.
no code implementations • 1 Dec 2015 • Marius Leordeanu, Alexandra Radu, Shumeet Baluja, Rahul Sukthankar
Our method works both as a feature selection mechanism and as a fully competitive classifier.
1 code implementation • 19 Nov 2015 • George Toderici, Sean M. O'Malley, Sung Jin Hwang, Damien Vincent, David Minnen, Shumeet Baluja, Michele Covell, Rahul Sukthankar
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements.